Skip to content

Reduce the host overhead of Minimax-M2#2228

Open
yangulei wants to merge 4 commits into
HabanaAI:aice/v1.22.0from
yangulei:minimax
Open

Reduce the host overhead of Minimax-M2#2228
yangulei wants to merge 4 commits into
HabanaAI:aice/v1.22.0from
yangulei:minimax

Conversation

@yangulei
Copy link
Copy Markdown

@yangulei yangulei commented Feb 3, 2026

Wei-Lin-Intel and others added 2 commits February 3, 2026 10:40
Signed-off-by: Youlei Yang <youlei.yang@intel.com>
Signed-off-by: Youlei Yang <youlei.yang@intel.com>
Signed-off-by: Youlei Yang <youlei.yang@intel.com>
Signed-off-by: Youlei Yang <youlei.yang@intel.com>
dtype=input_.dtype,
device=input_.device)
# All-gather.
htorch.core.mark_step()
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not safe to remove it. Sometimes it will cause hang or the accuracy issue.

# FIXME(kzawora): this is a workaround for a bug in Habana PT bridge
# occurring when PT_HPU_ENABLE_LAZY_COLLECTIVES=true env var is used
# (which is required for tensor parallel HPUGraph inference)
htorch.core.mark_step()
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not suggest to do it.

@github-actions
Copy link
Copy Markdown

This pull request has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this pull request should remain open. Thank you!

@github-actions github-actions Bot added the stale label May 13, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants